计算指定生辰的紫微斗数星盘，返回完整的星盘数据（包含十二宫、星耀、亮度等）。支持经纬度参数，将时间转换为真太阳时进行更精确的计算
AI agents call calculate_ziwei to retrieve information from 紫微斗数 MCP 服务器 (MCPIztro) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though calculate_ziwei only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
计算指定生辰的紫微斗数星盘，返回完整的星盘数据（包含十二宫、星耀、亮度等）。支持经纬度参数，将时间转换为真太阳时进行更精确的计算. It is categorised as a Read tool in the 紫微斗数 MCP 服务器 (MCPIztro) MCP Server, which means it retrieves data without modifying state.
Register the 紫微斗数 MCP 服务器 (MCPIztro) MCP server in PolicyLayer and add a rule for calculate_ziwei: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches 紫微斗数 MCP 服务器 (MCPIztro). Nothing to install.
calculate_ziwei is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the calculate_ziwei rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for calculate_ziwei. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
calculate_ziwei is provided by the 紫微斗数 MCP 服务器 (MCPIztro) MCP server (wuunicorn/mcpiztro). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.